Table 4 Comparison between test accuracy for the four proposed models based on ANN classifier.
From: Intelligent retinal disease detection using deep learning
Model name | Accuracy | Precision | Recall | F1-score | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Class 0 | Class 1 | Class 2 | Class 0 | Class 1 | Class 2 | Class 0 | Class 1 | Class 2 | |||||
Model A (DenseNet121 with PCA) | 97.4% | 0.99 | 0.97 | 0.96 | 0.99 | 0.95 | 0.96 | 0.99 | 0.96 | 0.97 | |||
Model B (MobileNetV2 with PCA and DWT) | 96.6% | 0.99 | 0.94 | 0.98 | 0.99 | 0.97 | 0.93 | 0.99 | 0.96 | 0.95 | |||
Model C (MobileNetV2, DenseNet121 with PCA and DWT) | 98.2% | 1.00 | 0.99 | 0.96 | 0.99 | 0.97 | 0.99 | 1.00 | 0.98 | 0.97 | |||
Model D (MobileNetV2 with PCA) | 98.1% | 0.99 | 0.98 | 0.97 | 0.99 | 0.97 | 0.98 | 0.99 | 0.98 | 0.98 | |||
